- agent_service: yield {"__sources": [...]} token instead of __meta for sources
- agent_service: inject Korean-only rule at top of system message before date
- config.py: strengthen Korean thinking instruction in system prompt
- ROADMAP: add Phase 25 entry
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
call_model now emits writer({"__start": True}) before LLM inference.
stream_response() converts it to {"__status": label} — distinct from
__meta so the UI shows it immediately without accumulating in the log.
Removes the 10-second silent wait before the first progress message.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
stream_response() now yields plain str for actual answer tokens and
{\"__meta\": str} dicts for progress/thinking/source metadata.
Consumers (WebUI, Telegram) can filter __meta tokens for TTS/display.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- api.py: FastAPI 앱 신규 생성
- GET /health, POST /chat (SSE), POST /reset, POST /ingest, GET/DELETE /documents
- SSE 포맷: data: <JSON 토큰>\n\n / data: [DONE]\n\n
- Bearer Token 인증 (API_TOKEN 미설정 시 개발 모드)
- user_id 파라미터로 멀티유저 지원 (기존 AgentService·DB 구조 재사용)
- config.py: api_token 필드 추가
- app.py: _get_agent에 query_rewrite_enabled 누락 수정
- requirements.txt: fastapi, uvicorn[standard], python-multipart 추가
- ROADMAP: Phase 22 ✅, Telegram Bot 클라이언트 예시 추가
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- query_rewrite 노드 추가 (agent → query_rewrite → tools 순서)
- route_after_agent: search_documents 호출 시에만 query_rewrite 라우팅, 그 외 직접 tools
- tools_condition(prebuilt) 제거 → 커스텀 라우팅 함수로 대체
- query_rewrite_node: 구어체 쿼리를 키워드 중심 문장으로 변환
- 이전 대화 2턴 컨텍스트로 대명사·지시어 해소
- enable_thinking=False 바인딩으로 불필요한 사고 과정 제거
- __query_rewrite 커스텀 이벤트 emit → RAG_VERBOSE 시 변환 결과 출력
- QUERY_REWRITE_ENABLED=true 로 활성화 (기본값 false)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- FastEmbedSparse(Qdrant/bm25) 기반 sparse 임베딩 추가 (fastembed 패키지)
- IngestionService: HYBRID_SEARCH_ENABLED 시 dense + sparse 동시 저장 (RetrievalMode.HYBRID)
- _ensure_collection_schema(): sparse vector 미설정 컬렉션 자동 삭제·재생성
- RetrieverService: hybrid 스토어 + dense 폴백 구조, Qdrant 내장 RRF로 결과 통합
- container.py: sparse_embeddings Singleton 프로바이더, ingestion/retriever 양쪽 주입
- .env.example: HYBRID_SEARCH_ENABLED, SPARSE_MODEL_ID 항목 추가
활성화: .env에 HYBRID_SEARCH_ENABLED=true 설정 후 기존 문서 재수집 필요
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Prepend today's date to system prompt on every call so LLM uses correct year
- Calculate both Korean age (현재연도-출생연도+1) and 만 나이 with exact birthday handling
- Support full date (생년월일) and year-only (생년) profile values
- Update remember_user_info to encourage storing full birth date
- Strengthen get_current_date tool description for age-related queries
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- **Implement `MlxModelService` for local LLM backend.**
- **Introduce `DatabaseService` for MySQL integration.**
- **Add `HistoryService` to manage conversation context.**
- **Set up CLI interface via `CliUiService`.**
- **Establish EventBus for token streaming.**
- **Include conversation repository for data persistence.**
- **Add environment-based configuration management.**
- **Draft IoC architectural plan.**
shinalok